Mean Absolute Percentage Error

A Simple Explanation - By Varsha Saini

What is MAPE?

Mean Absolute Percentage Error, also called MAPE is commonly used to measure the performance of time series forecasting. As the name denotes, Mean Absolute Percentage Error is the mean of absolute percentage error in forecasting where error is the difference between the actual value and the forecasted value.

MAPE Formula

Below is the formula for Mean Absolute Percentage Error:


  • n = sample size
  • actual = actual value
  • forecast = the forecasted value

The lower the MAPE, the better the model’s ability to forecast the values.

Advantages of MAPE

  1. It cancels out the effect of positive and negative errors.
  2. It is easy to understand as the error is in terms of percentage. For eg, 5% MAPE means that the average distance between the actual and forecasted value is 5%.

Points to Note

  1. MAPE shouldn’t be used for small data.
  2. The value of MAPE will be 0 if the actual value is not available.